Nicholas Pfaff
Papers
2
Total Citations
8
H-Index
2
About
Nicholas Pfaff is an emerging researcher at the intersection of robotics, simulation, and machine learning, with a focus on bridging the gap between simulated and real-world environments for robotic manipulation tasks. His work addresses one of the most pressing challenges in modern robotics: efficiently transferring learned behaviors from simulation to physical systems. Pfaff's most notable contribution, "Scalable Real2Sim," introduces a fully automated pipeline for generating physics-accurate simulation assets from real-world objects using robotic pick-and-place setups — eliminating the labor-intensive manual measurements that have historically bottlenecked digital twin creation. This work, already accumulating 6 citations since its 2025 publication, represents a meaningful step toward scalable robot learning infrastructure. His complementary research on sim-and-real cotraining of diffusion policies for planar pushing tasks further deepens understanding of how simulation data can be strategically combined with real hardware demonstrations to improve imitation learning outcomes. Though early in his career, Pfaff's research tackles foundational questions about simulation fidelity, dataset design, and automated asset creation — areas increasingly critical as the robotics community scales toward more generalizable, data-driven manipulation systems. His contributions position him as a promising voice in robot learning research.
Research Focus
Key Achievements
Top Papers
- 1
- 2